EPUB Input: Handle files that have duplicate entries in the spine

src/calibre/ebooks/conversion/plugins/epub_input.py

@@ -198,11 +198,13 @@ class EPUBInput(InputFormatPlugin):
                 ('application/vnd.adobe-page-template+xml','application/text'):
                     not_for_spine.add(id_)
 
+        seen = set()
         for x in list(opf.iterspine()):
             ref = x.get('idref', None)
-            if ref is None or ref in not_for_spine:
+            if not ref or ref in not_for_spine or ref in seen:
                 x.getparent().remove(x)
                 continue
+            seen.add(ref)
 
         if len(list(opf.iterspine())) == 0:
             raise ValueError('No valid entries in the spine of this EPUB')

src/calibre/ebooks/metadata/opf2.py

@@ -286,15 +286,17 @@ class Spine(ResourceCollection): # {{{
     @staticmethod
     def from_opf_spine_element(itemrefs, manifest):
         s = Spine(manifest)
+        seen = set()
         for itemref in itemrefs:
             idref = itemref.get('idref', None)
             if idref is not None:
                 path = s.manifest.path_for_id(idref)
-                if path:
+                if path and path not in seen:
                     r = Spine.Item(lambda x:idref, path, is_path=True)
                     r.is_linear = itemref.get('linear', 'yes') == 'yes'
                     r.idref = idref
                     s.append(r)
+                    seen.add(path)
         return s
 
     @staticmethod

src/calibre/ebooks/pdf/writer.py

@@ -221,7 +221,7 @@ class PDFWriter(QObject): # {{{
             self.tmp_path = PersistentTemporaryDirectory('_pdf_output_parts')
 
     def insert_cover(self):
-        if self.cover_data is None:
+        if not isinstance(self.cover_data, bytes):
             return
         item_path = os.path.join(self.tmp_path, 'cover.pdf')
         printer = get_pdf_printer(self.opts, output_file_name=item_path,